Evaluation of Segmentation Quality via Adaptive Composition of Reference Segmentations

Bo Peng, Lei Zhang, Xuanqin Mou, Ming Hsuan Yang

Research output: Contribution to journalArticlepeer-review

10 Citations (Scopus)

Abstract

Evaluating image segmentation quality is a critical step for generating desirable segmented output and comparing performance of algorithms, among others. However, automatic evaluation of segmented results is inherently challenging since image segmentation is an ill-posed problem. This paper presents a framework to evaluate segmentation quality using multiple labeled segmentations which are considered as references. For a segmentation to be evaluated, we adaptively compose a reference segmentation using multiple labeled segmentations, which locally matches the input segments while preserving structural consistency. The quality of a given segmentation is then measured by its distance to the composed reference. A new dataset of 200 images, where each one has 6 to 15 labeled segmentations, is developed for performance evaluation of image segmentation. Furthermore, to quantitatively compare the proposed segmentation evaluation algorithm with the state-of-the-art methods, a benchmark segmentation evaluation dataset is proposed. Extensive experiments are carried out to validate the proposed segmentation evaluation framework.

Original languageEnglish
Article number7723880
Pages (from-to)1929-1941
Number of pages13
JournalIEEE transactions on pattern analysis and machine intelligence
Volume39
Issue number10
DOIs
Publication statusPublished - 2017 Oct 1

Bibliographical note

Funding Information:
This work was supported by the HK RGC GRF Grant (No. PolyU 5315/12E), the NSFC (Nos. 61202190, 61571359), the National Key Basic Research Program (2016YFA0202003) and US National Science Foundation CAREER Grant (No. 1149783).

Publisher Copyright:
© 1979-2012 IEEE.

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'Evaluation of Segmentation Quality via Adaptive Composition of Reference Segmentations'. Together they form a unique fingerprint.

Cite this